© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93223
    Prev
    Next
    INDEX
    Explanations

    Alaska or Finland

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alaska
    -1.11
    Alaska
    -0.95
     Maine
    -0.89
    Maine
    -0.75
    DebuggerNonUser
    -0.75
     Minnesota
    -0.73
    Minnesota
    -0.72
     Finland
    -0.71
     Alaskan
    -0.71
    alaska
    -0.67
    POSITIVE LOGITS
    <bos>
    0.65
    errHandler
    0.59
     intérieure
    0.57
    saraba
    0.54
    ουσ
    0.54
    ImageIO
    0.52
     finitely
    0.50
     fusca
    0.50
     indépendante
    0.49
     Alligator
    0.48
    Activations Density 1.242%

    No Known Activations